Triple

T13800310
Position Surface form Disambiguated ID Type / Status
Subject Liseberg station E331621 entity
Predicate ownedBy P347 FINISHED
Object Jernhusen E462905 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Jernhusen | Statement: [Liseberg station, ownedBy, Jernhusen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jernhusen
Context triple: [Liseberg station, ownedBy, Jernhusen]
  • A. Jernhusen chosen
    Jernhusen is a Swedish state-owned real estate company that owns, develops, and manages railway stations and related transport properties across Sweden.
  • B. Bruttenholm
    Bruttenholm is the surname of Professor Trevor Bruttenholm, the fictional British occult scholar and adoptive father of Hellboy in Mike Mignola’s comic series and its film adaptations.
  • C. Hjorthagen
    Hjorthagen is a residential district in northeastern Stockholm, Sweden, known for its mix of historic workers’ housing and modern developments near the Royal National City Park and the Värtan harbor area.
  • D. Hestnes
    Hestnes is a small settlement located within the municipality of Eigersund in Rogaland county, southwestern Norway.
  • E. Tjuneroy
    Tjuneroy was an ancient Egyptian official, likely a high-ranking scribe or priest under Ramesses II, associated with the creation of the Saqqara King List.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d81c58feb08190a77bca8bf7d6d20f completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de025ce9148190b23370f6a522ff7a completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b0893a20819081d4001b8dbc9c36 completed May 3, 2026, 8:31 p.m.
Created at: April 9, 2026, 10:11 p.m.